Home » News » What? ‘AI-generated art’? What Does it Even Means?

What? ‘AI-generated art’? What Does it Even Means?

fb twitter pinterest linkedin
What? ‘AI-generated art’? What Does it Even Means?-GadgetAny

The latest viral sensation taking over the internet is all thanks to a genius AI image generator that creates any photo, users can imagine. Lately, if you have been on Twitter, you have probably had a glimpse of some combination of pretty strange images taking over your timeline.

These images are the result of an AI generator called ‘Dall- E2 Mini’, which is able to create completely original images based on the user’s prompt. ‘Dall-E2 Mini’: ‘Dall -E, cleverly named after the Spanish artist Salvador Dali and Disney’s lovable character Wall-E.

More interestingly, these images are certainly more accurate, resulting in hilarious and sometimes downright confusing pictures based on people’s imagination.

Dall- E2 Mini

How does it work?

Specifically, the working of the program is a bit complicated, essentially. The Dall-E2 Mini is able to create these images using automated text descriptions of pictures to generate photos based on what users actually want.

The algorithms identify patterns in the images and captions and eventually can start predicting what captions and images go together. Once a model can predict what an image “should” look like based on a caption, the next step is reversing it – creating entirely novel images from new “captions”.

How to use the Dall-E2 Mini?

To create your own horrific AI-generated images, just head over to the Dall-E2 Mini website and type in whatever you can think of.

It might take a little while to load your results, but the end product is certainly worth the wait.

Dall- E2 Mini

Will it replace human visual artists?

Although, anyone knows what will happen to artists. But there are still so many edge cases where these models break down that I wouldn’t be relying on them exclusively.

So right now it’s just about good enough for memes, and still makes weird nightmare images (especially of faces), but not as much as it used to. But who knows about the future.

The above excerpts have been taken from the conversation between Patrick Lum(Writer, Guardian Australia) and Josh Nicholas (Data journalist from Guardian Australia)

Prelo Con

By Prelo Con

Following my passion by reviewing latest tech. Just love it.

Related news